Switching Loss for Generalized Nucleus Detection in Histopathology
This addresses class imbalance in medical image analysis for tasks like nucleus detection and segmentation, offering a practical improvement over existing loss functions.
The authors tackled class imbalance in medical image detection and segmentation by proposing a switching loss function that adaptively shifts emphasis between foreground and background classes per mini-batch, leading to a nucleus detector that outperformed existing methods on source and target datasets without retraining, and improved ventricle segmentation in MRI.
The accuracy of deep learning methods for two foundational tasks in medical image analysis -- detection and segmentation -- can suffer from class imbalance. We propose a `switching loss' function that adaptively shifts the emphasis between foreground and background classes. While the existing loss functions to address this problem were motivated by the classification task, the switching loss is based on Dice loss, which is better suited for segmentation and detection. Furthermore, to get the most out the training samples, we adapt the loss with each mini-batch, unlike previous proposals that adapt once for the entire training set. A nucleus detector trained using the proposed loss function on a source dataset outperformed those trained using cross-entropy, Dice, or focal losses. Remarkably, without retraining on target datasets, our pre-trained nucleus detector also outperformed existing nucleus detectors that were trained on at least some of the images from the target datasets. To establish a broad utility of the proposed loss, we also confirmed that it led to more accurate ventricle segmentation in MRI as compared to the other loss functions. Our GPU-enabled pre-trained nucleus detection software is also ready to process whole slide images right out-of-the-box and is usably fast.